© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 10561
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events that happen after a specific point in time

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "after" followed by numeric values, indicating time-related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aez
    -0.76
    NRS
    -0.70
    cci
    -0.70
    eto
    -0.67
    odiac
    -0.66
    âĸĪâĸĪâĸĪâĸĪ
    -0.66
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.66
    Mask
    -0.65
    aq
    -0.65
    Davis
    -0.64
    POSITIVE LOGITS
    noon
    1.05
    market
    1.02
    thought
    0.87
     finishing
    0.84
     completing
    0.83
    wards
    0.80
     acquiring
    0.79
    word
    0.78
     supper
    0.77
     inspecting
    0.77
    Activations Density 0.108%

    No Known Activations